FDFENet: Cropland Change Detection in Remote Sensing Images Based on Frequency Domain Feature Exchange and Multiscale Feature Enhancement

He Y. Qian Y. Wang X. Bai L. Wang Y. Wei H. Huang X. Lv J. Yang X. Duan M. Gong W. Mansurova M.
January 2026 Multidisciplinary Digital Publishing Institute (MDPI)

Remote Sensing
2026 #18 Issue 1

Highlights: What are the main findings? FDFENet unifies spatial modeling with frequency domain style alignment to address style and ground object differences. Two scene-adaptive frequency modules further strengthen robustness to complex scenarios. FDFENet achieved state-of-the-art performance on the cropland benchmark dataset (CLCD), with an F1 score of 77.09% and an IoU of 62.72%, outperforming both CNN-based and Transformer-based methods. What are the implications of the main findings? FDFENet’s spatial–frequency collaboration offers a learnable paradigm for cross-domain feature fusion and hybrid architecture design in intelligent remote sensing interpretation. The FDFENet framework demonstrates high generalization capability and performance, providing technical support for large-scale cropland protection and monitoring urban expansion. Cropland change detection (CD) in high-resolution remote sensing images is critical for cropland protection and food security. However, style differences caused by inconsistent imaging conditions (such as season and illumination) and ground object scale differences often lead to high numbers of false and missed detections. Existing approaches, predominantly relying on spatial domain features and a multiscale framework, struggle to address these issues effectively. Therefore, we propose FDFENet, incorporating a Frequency Domain Feature Exchange Module (FFEM) that unifies image styles by swapping the low-frequency components of bitemporal features. A Frequency Domain Aggregation Distribution Module (FDADM) is also introduced as a comparative alternative for handling style discrepancies. Subsequently, a Multiscale Feature Enhancement Module (MSFEM) strengthens feature representation, while a Multiscale Change Perception Module (MSCPM) suppresses non-change information, and the two modules work cooperatively to improve detection sensitivity to multiscale ground objects. Compared with the FDADM, the FFEM exhibits superior parameter efficiency and engineering stability, making it more suitable as the primary solution for long-term deployment. Evaluations on four CD datasets (CLCD, GFSWCLCD, LuojiaSETCLCD, and HRCUSCD) demonstrate that FDFENet outperformed 13 state-of-the-art methods, achieving F1 and IOU scores of 77.09% and 62.72%, 81.81% and 73.63%, 74.47% and 59.32%, and 75.95% and 61.23%, respectively. This demonstrates FDFENet’s effectiveness in addressing style differences and ground object scale differences, enabling high-precision cropland monitoring to support food security and sustainable cropland management.

cropland change detection , deep learning , frequency feature , multiscale feature , remote sensing images

Text of the article Перейти на текст статьи

School of Computer Science and Technology, Xinjiang University, Urumqi, 830046, China
Joint International Research Laboratory of Silk Road Multilingual Cognitive Computing, Xinjiang University, Urumqi, 830046, China
School of Artificial Intelligence, Tianjin University, Tianjin, 300354, China
Key Laboratory of Software Engineering, Xinjiang University, Urumqi, 830091, China
Xinjiang Engineering Research Center of Big Data and Intelligent Software, School of Software, Xinjiang University, Urumqi, 830091, China
School of Information Technology and Communication, Hexi University, Zhangye, 734000, China
Department of Artificial Intelligence and Big Data, Al-Farabi Kazakh National University, Almaty, 050040, Kazakhstan

School of Computer Science and Technology
Joint International Research Laboratory of Silk Road Multilingual Cognitive Computing
School of Artificial Intelligence
Key Laboratory of Software Engineering
Xinjiang Engineering Research Center of Big Data and Intelligent Software
School of Information Technology and Communication
Department of Artificial Intelligence and Big Data

10 лет помогаем публиковать статьи Международный издатель

Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026